[{"data":1,"prerenderedAt":137},["ShallowReactive",2],{"project-40042395":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":5,"maker":10,"posted_at":11,"year":12,"points":13,"comments":14,"rank_in_year":15,"shown_in_year":16,"top":17,"tier":18,"category":19,"subcategory":20,"format":21,"keywords":22,"reception":27,"sentiment":28,"stance_mix":29,"scored_comments":31,"aspects":32,"strip":35,"post_text":36,"what":37,"said":51,"maker_in_thread":83,"shape":87,"grid":89,"attempts":97,"same_week":98,"maker_shows":129,"maker_hidden":130,"reader_version":131,"card":132},"40042395","edgematic.dev","Reduce ChatGPT costs 10x with distributed cache for LLMs","title","Show HN: Reduce ChatGPT costs 10x with distributed cache for LLMs","https:\u002F\u002Fedgematic.dev\u002Fgpt-cache-llm","zaiste",1713197254,2024,22,3,1827,3515,52,"shown","infrastructure","caching for llm apis","api",[23,24,25,26],"llm cache","chatgpt cost","semantic cache","edge caching","quiet",null,{"positive":30,"neutral":31,"mixed":30,"critical":30},0,2,{"pricing":33,"idea":34},{"positive":30,"critical":30},{"positive":30,"critical":30},[14,30,14],"Hello HN!\n\nWe're building a caching solution for LLMs (ChatGPT, Claude). By combining cutting-edge approaches, such as edge computing, prompt compression, vectorization, and others - it can reduce your AI bills by up to 10x and significantly lower response times.\n\nKey Features: - cost efficiency: our system stores frequent queries, reducing the number of upstream (paid) API calls - fast responses: with various nodes globally, we reduce latency by serving data from the nearest location - scalability: designed to handle increasing loads and data sizes without degrading performance.\n\nThe cache op",{"problem":38,"audience":44,"pricing":28,"motivation":28,"time_to_build":28,"stack":48,"openness":49,"stage":50,"team_size":49},{"value":39,"source":40,"evidence":41},"High cost and latency of paid LLM API calls such as ChatGPT and Claude","maker",[42],{"id":43},"post",{"value":45,"source":40,"evidence":46},"Teams running LLMs in production where cost and response time matter",[47],{"id":43},[],"unknown","prototype",{"praise":52,"objections":53,"requests":60,"questions":69,"alternatives":74},[],[54],{"value":55,"source":40,"evidence":56},"No concrete data yet on savings; the 10x claim is anecdotal",[57],{"id":58,"by":10,"text":59},"40043700","We are still exploring. We don’t have any concrete data yet, but in some instances, we've observed reductions up to ten times. This seems especially relevant to specific areas,…",[61],{"value":62,"source":63,"evidence":64},"Share the 'how much will it save' numbers and a demo","commenter",[65],{"id":66,"by":67,"text":68},"40043552","throwaway888abc","Looks great, do you have any concrete data how much money it will save ? Also, how does it compare to for example GptCache[0] ? or any other semantic cache solution[1] ? [0]…",[70],{"value":71,"source":63,"evidence":72},"How does it compare to GptCache and other semantic caches?",[73],{"id":66,"by":67,"text":68},[75,79],{"value":76,"source":63,"evidence":77},"GptCache",[78],{"id":66,"by":67,"text":68},{"value":80,"source":63,"evidence":81},"Portkey semantic cache",[82],{"id":66,"by":67,"text":68},{"comments":84,"answered":84,"key":85},1,[86],{"id":58,"text":59},{"commenters":31,"max_depth":14,"maker_replies":84,"first_comment_mins":88,"lifespan_hours":31},99,[90,92,94],[66,30,14,91,67,30],"project\u002Fneutral\u002Fpricing",[58,30,30,93,10,84],"maker\u002Fneutral\u002Fnone",[95,30,14,96,67,30],"40044092","project\u002Fneutral\u002Fidea",[],[99,104,109,114,119,124],{"id":100,"name":101,"points":102,"category":103},"40003710","OptiGap sensor",886,"hardware",{"id":105,"name":106,"points":107,"category":108},"40041198","gypsum",552,"learning_science",{"id":110,"name":111,"points":112,"category":113},"40017180","Mazelit",517,"games",{"id":115,"name":116,"points":117,"category":118},"40033490","markdowndown",441,"productivity",{"id":120,"name":121,"points":122,"category":123},"40067677","Effort",419,"ai",{"id":125,"name":126,"points":127,"category":128},"40028111","index advisor",417,"data",7,false,"v2",{"id":133,"name":5,"line":6,"ai":130,"cat":19,"year":12,"points":13,"comments":14,"rec":27,"s":28,"top":17,"kw":134,"maker":10,"domain":5,"tier":18,"attempts":30,"strip":135,"url":9,"mix":136,"praise":-1,"objection":55,"sub":20},40042395,[23,24,25,26],"303",[30,31,30,30],1793991089013]